Train text classification model using vectors.tsv and metadata.tsv

Hi,

I have trained a text classification model that uses pre-trained word embeddings as per this guide https://keras.io/examples/nlp/pretrained_word_embeddings/

Next, I would like to take use the vectors.tsv and metadata.tsv generated by your code, to train a new text classification model.

The Keras guide in the link above has the following code:
from tensorflow.keras.layers import Embedding embedding_layer = Embedding( num_tokens, embedding_dim, embeddings_initializer=keras.initializers.Constant(**embedding_matrix**), trainable=False, )

I think the vectors.tsv file needs to be coverted into an array of floats to be used as embeddings_initializer. But I'm not sure what else needs to be done.

Do you have an additional guide on how to train text classification model using a new word embedding?

Start with the Keras pretrained word embeddings guide linked in the issue and inspect how vectors.tsv and metadata.tsv are generated. Determine whether those files are intended as inputs for an embedding layer and document the required conversion and vocabulary mapping. Done means a clear guide or example shows how to use these files for text classification.